library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.2 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(lubridate)
library(plotly)
##
## Attaching package: 'plotly'
##
## The following object is masked from 'package:ggplot2':
##
## last_plot
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following object is masked from 'package:graphics':
##
## layout
Read in data
path <- "../data/marathon_results_2017.csv"
marathon <- read_csv(path)
## Warning: One or more parsing issues, call `problems()` on your data frame for details,
## e.g.:
## dat <- vroom(...)
## problems(dat)
## Rows: 26410 Columns: 22
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (10): Bib, Name, M/F, City, State, Country, 10K, 15K, 20K, Proj Time
## dbl (4): Age, Overall, Gender, Division
## time (8): 5K, Half, 25K, 30K, 35K, 40K, Pace, Official Time
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
colnames(marathon)
## [1] "Bib" "Name" "Age" "M/F"
## [5] "City" "State" "Country" "5K"
## [9] "10K" "15K" "20K" "Half"
## [13] "25K" "30K" "35K" "40K"
## [17] "Pace" "Proj Time" "Official Time" "Overall"
## [21] "Gender" "Division"
Interactive Plot
Top 25 runners
p1_data <- marathon %>%
group_by(Country) %>%
summarise(fastest_time = min(`Official Time`),
fastest_runner = Name[which.min(`Official Time`)]) %>%
arrange(fastest_time) %>%
head(15)
top15 <- ggplot(data = p1_data, mapping = aes(x = fastest_time, y = fct_reorder(Country, fastest_time, .desc = TRUE))) +
geom_col(aes(fill = Country), color = "lightgray", alpha = 0.3) +
geom_text(aes(label = `fastest_runner`), nudge_x = -3000, ) +
scale_x_continuous(limits = c(0, 11000)) +
labs(
title = "Top 15 Runners by Country",
subtitle = "2017 Boston Marathon",
x = "Time in Seconds",
y = ""
) +
theme(
legend.position = "none",
plot.title = element_text(hjust=0.5, vjust=2, size=14),
plot.subtitle = element_text(hjust=0.5, vjust=3)
)
top15

ggplotly(top15)
Spacial visualization of the number of racers per state in USA
unwanted <- c("AA", "AE","AP","MH","GU","PR","VI","DC")
USA_runners <-
marathon %>%
filter(Country == "USA") %>%
filter(!State %in% unwanted) %>%
group_by(State) %>%
summarise(num_runners = n())%>%
rename(state = State)
USA_runners %>%
filter(state == "MA") %>%
pull
## [1] 4586
USA_runners %>%
filter(!state == "MA") %>%
summarise(total_other = sum(num_runners))
## # A tibble: 1 × 1
## total_other
## <int>
## 1 16171
Using usmap to create spatial visualization
- I attempted to use the USA shapefiles and
sf package
- However, I learned a very hard lesson in trying to manually adjust
size and shape of the entir plot margins
- I could not get it zoomed in enough to see details
- Which lead me to use this package
library(usmap)
plot_usmap(data = USA_runners, values = "num_runners") +
scale_fill_continuous(low = "lightblue", high = "black", name = "Number of Runners", label = scales::comma) +
labs(title = "US Participation by State", subtitle = "2017 Boston Marathon") +
theme(
plot.title = element_text(hjust=0.5, vjust=0, size=14),
plot.subtitle = element_text(hjust=0.5, vjust=0),
legend.position = "right"
)

us_participation <- plot_usmap(data = USA_runners, values = "num_runners") +
scale_fill_continuous(low = "lightblue", high = "black", name = "Number of Runners", label = scales::comma) +
labs(title = "US Participation by State", subtitle = "2017 Boston Marathon") +
theme(
plot.title = element_text(hjust=0.5, vjust=0, size=14),
plot.subtitle = element_text(hjust=0.5, vjust=0)
)
ggplotly(us_participation)
Models
How much does age affect your official time
- Hypothesize the relationship between
Age and
Official Time to be highly positively correlated
- Why?
- As we get older, our marathon times would increase
- However we can see that in the ages from 20-40 there are many
runners who had extrememly fast times
- Conclusion is in general, yes there is a positive correlation, it is
not highly correlated however as we can tell from our linear model
ggplot(data = marathon, aes(x = Age, y = `Official Time`)) +
geom_point( alpha = 0.1) +
geom_smooth(method = "lm") +
facet_wrap(~`M/F`)
## `geom_smooth()` using formula = 'y ~ x'

Let’s take a look at an extreme correlation
- Hypothesize the quicker a runner’s pace is, the faster they will
finish
- Why?
- The math just seems to add up here :)
- Conclusion, extreme correlation!
ggplot(data = marathon, aes(x = Pace, y = `Official Time`)) +
geom_point( alpha = 0.1) +
geom_smooth(aes(color = `M/F`), method = "lm") +
facet_wrap(~`M/F`) +
theme(
legend.position = "none"
)
## `geom_smooth()` using formula = 'y ~ x'
